diff --git a/_init_1.5B_seed43/0/lr_scheduler/lr_scheduler_pp-0-of-1_tp-0-of-1_exp-0-of-1.pt b/_init_1.5B_seed43/0/lr_scheduler/lr_scheduler_pp-0-of-1_tp-0-of-1_exp-0-of-1.pt new file mode 100644 index 0000000000000000000000000000000000000000..c1248d7daa36f48aa2659cf759508ba33bc30df3 --- /dev/null +++ b/_init_1.5B_seed43/0/lr_scheduler/lr_scheduler_pp-0-of-1_tp-0-of-1_exp-0-of-1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61cd9db5cd452564f4c66b062fabb1add7a2d292d19a5155edb8af8ee3c61bb9 +size 4784 diff --git a/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d64f9141dc7f5ebbe41173db13aba201c083dfe4 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ddc42a164d2796d0b02a4f664bd8bbd7b33f91f945fbcee4e5487ec744527c7 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a3eeae328b757964510f1adf333f0010af7f91c8 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2845a87491999b968fcb89644413b3dbb1070ee0932bfb3c6dae5fb68639c558 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..52a81ce70d26af4b85a3e82910eca8680ef069b3 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2583c7153680f22facb703e3925fde167543dd2896a09900d7d27f584d29ffd6 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..24c806af3b9969aa171692708434871ff027f2b1 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2134981b223dd9f39970ae5045eedaeb4b53c17866ffa383bfc4df41927c00b0 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce85ca2f61930ea1de3c0ac674bed80d92c08607 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:619e14d5c3745f36d92354aa7dfe97fa03deb55ff616bc6ccc8c1a31dd61861f +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..10815234354a0f8527557f46596f4629e7a37afa --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea913f2114c05aa1d9da87f81ff0f497355a3cff1c5a4f0000f712830325253 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d00483e42b9dd797ab96dd79c04a14bbeee73d7d --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01e0982ee897cc7a863fc135467ce4e84796fa8f15c43bc4b4c56b09834a2013 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..751c898f7d54c31be44a6a18b221d80ce5db6f1f --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e89292749d1230d364ec90e0168464e9c02dca775065127f22650415a2badaea +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..04a4d7ca2208380cb262d3336d1db1c60bbd9702 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b962792ab600b877997f98079b3f385561921bb65edb3a5c3a84113f3c1932f +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b20061763c82300cfc45d8936f0873bab7cc0aa9 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de0f77d745000c5037829b64d0aef0ab22666ec76162038845c035c31575edce +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2852a8d5e02b24123726b5a35034db2165fd3f7f --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:837198a23dd538200161f4856ef3bed98b859a904040044c7ba4fa4dc41852b7 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1376551e090c8e98d149e4bbdf6d02dde34dbdea --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46a5e53b254c80ab25616b68469ecf734f5c9701b7eeae3acfad9926da3e2e99 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/10/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7cf47403cdbce8d11ca8bf6c73f3e7b3c3463607 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d31a4c797134b8529e99fc3969a89ba1723226ed3583c866ceac31c2adcca6 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a65c232a814e1b39c1de3785d6ed6244c80aadb --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a080396dc747613f436bf88a85a9194bdee2a4debc44cebf403db7805a64578 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..69375937a427eefdd3a888e6654fa26ee2de0128 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:344440e95b18c732566235969301e6f91dc03a08146777cb0c31d5bacaf13d74 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d270a461032ee5bd3c32726f8e0dff9ecd2a1940 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0e3595daea0bc8bfc7c59209898f09f051d0ecc44bdd2ea92368ab4a64c35ca +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/11/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a8a4d06dabf9ae9c385239187ab3126986feb391 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01c80cdbbdf9af0f6b0801b0f65df1b0c46f1a01d055da088ea420a4e4c1503d +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a1bde234b239e3c3829a916f9702f5a8eab5388 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa150ff018115fe3a79b312e2d5c556a3311d6f00af3bb42438d50eec8baa4a4 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f92571ca4507c4257b69804d95c21a3c07341398 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88c54b451332e19a985f25d90a64984768364c65d89ad24122e139b3163fc44f +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e59959a21124785582c713efbeca8ce943fe8058 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f15d0378342e99887ff92a2095c25d155080edc9f15abd2b45026713de32c0 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/12/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1994291555790bcd743c828e967a335f5cb7597a --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18be786b867c37a70f9cbefb0d83847cd50a18ff027814b2614423cbad060a0 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc4c3449b7c1920d7dac8ea2e11c9c020030dfd3 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:230041d455ed1543e0de4d9568a719170c9b56787e47e8c8b523be7c977459d9 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c49cc9bb973e9a43de8b73365cc69373a6c90936 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ca652c8c3bcf3fde20a910b9fe5bc03f300316eea09508dd7c0e8349e6d67b2 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3607d7a411cfc84fb4fd16972dbbf9ff29815f7a --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59fb678a35bfc3a6c1371545f0e542e30a7050507800434e4104ede3b4691657 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a9094af08c4f420bfc0b32d97fb444689032d5ac --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b5e5512d5f8d829f9693a7e14f7d467731961c9db76f00b57cf8cc915aa4df +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..82540032b3cbd7bf4a1485799bba1521088b9a67 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:959016601e60b925246cda8e9ff0c4775f0a44d51d5fc4bceac38e3c4571bde1 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c48ab2397d14cc8cc1585e45c4d369c37aab4e8 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91771217548f9ee8abb003aacc02d137aa380e11709b2dfd46976156aab6f2bc +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a69aeab8d81dd831b65a5ad65a0f85933bc245a9 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1929dea440bf26041e820a437ad3f7f9ba9e8ad419961efcccfb67236c9c643f +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/14/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7405c4516a844099c378da73f07436c88444f4a --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ee798d185616571ed43c3d4912881a65b7221efc6870a37cf3b88ae6a56b59f +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..be131f6be9cd5ea00f63be79e2d83536712bb2b1 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62647eb4df64f7aadfe3cefb8e2f5f651fe203430f0fb2cd48812f7a6c2b5b26 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6040e25964e498b1ee8104e94fbe0d6e220e679f --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9133a4a894aac0d5106d36ed11a15f2c956687cd0f7931f0ffb7f959334c9c7 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eb9d1ceb9069f4975f47cb1e23b8a458b98e13ca --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b4f9cbf4b7d948f545b8e1490b98c292ad77f30d356e0df1f3b3da8e55dafb +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/15/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a4b6030e4cb983a7c2057da8e23782a9363e3d0d --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b008ef4b206cc9261b4194b5762c9a2e3bd29d3daf55b76e86775233e5e0825 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ea709e62a0b827b8986ca729513e0934e26c916 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d505632252b824d6a5a2df1da1aa3f42f0e5818378dc50e2cc93e8b922d6569 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a742b91b5b1ffb000e8197452790e4995e0a5c7 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f134d33b8cd5c152da042f1ebd92515cb3a31ac40cc17fa398da72496657bb76 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fed7017144cb79e6d5bf70c4dbfadebcc69c09e8 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e4535290e75acb6d80ca14c253be923e1806b274e4ce4cceeb51142bb665751 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/16/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5b99c07376429806ee99cdb1e27ae0e4cd1270af --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e4d8fb40d953a2e0220901d6f5d575a910809df95061cdc7d38fee68132a79 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c9ebc40eca1426c76f439e2d80684db1fe60489f --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a41ff152bf3ff05598415f2ff0beb2a6703e8782e1c571689a44eae780713ec4 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d80935e6779901a29ce1e253e5ee449375da9229 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e2e591f42428d58cab07a4bea488ccda66ad29e52abeb453110a41da636f23 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a7827175baa27a88399c59fdc0b37404ff18dbe --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c23a4361bfff505bc3ab713c983e3196269f2519324b636706a52e426de3132 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/17/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5fec97f11f5d5e74360dac3191100fcecfedd66c --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb68aaa7501ca0adc0e3cb2aa61b938dc4ef944562f0dbd6f049102363ccdcb5 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..280c621f039c16c91722e6f2372fd8aff4118d58 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a70fbc457e0bb05e4cced02bb2a3252ca3cfaf583bf42deea5d18bda9f776f3 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e46b180d0eb173499efdd24425e6d6993feca2a --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc57d7dbe4e80272ca940ef51b9fe6c90a19d313309b6254b8d1205de1c392c0 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd24ca662ce281d73991fe9bd8ba6abc592d55fd --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fea7c9eccceeee63ed0d924ab8184f7d5712ec003ca22b45409f64b812bedd58 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/18/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c3b7130f912f8bb20a8620868ae7ac8f96ee70b8 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:019093c24204c90f69ad77935a96afaed1eb0a1703c18dd4f49ada33ed5e0a74 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d0cccf9df62f227d3099b844b1e8237f64740723 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e43178067c3456e279fc8536182d289fcbffe764dc55f843deb498552a5e98b5 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7b871d349a42b37b2668e2a58e4482efe2dfd47 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b4e84a4148c4bac654d3c109beb3f9ed4b67292907cfe9f2ba3424444c651c +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e2e3b8f82075f044ed288163a13d1546968ba5d --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd94f7d155a3782f2a6849626cdc7c466e51d7e648fcfce9f45017799f42f862 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/19/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1bc019a7906962ceafcf49d7bd4bf3b0f9869acf --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7b9f7a17133c1bf0965186d80870a5248c41614d035cb7be4c5f568e95d52aa +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6aab4a2daff61802291d30e1353dde43229f3758 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f41a6c9226865776a8f2b9849f406d06f08a5e1e8e54bd9211ba95913381fbfa +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..18317523d9bd9a6ad683b5406482726cbe37d33f --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39bbdb3c4741f139963eb2e221bd4bc9146c0b834600da2cd7ed316266035ac9 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc1af758eeb38a3b90d7cac078454fe51a1cc299 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b78efb3ae8e63bc634669fed889044c147e57cda121ec0d6a7183d1b10445d7d +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/2/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0df3cd572cd4e73854fd95930e4feb12eed333d --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da0d88813f338f93356fec1e665ed63d6f6e90c772621cc20a50907c0424af5c +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..151acf31a95ba732be32d6d8b31d24c617c509cc --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab1bc763c2783e4a20b22aca6199785afef042f4bc85e75f737f5866c5f48277 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4cc61341b9162854fc37d64804b7c3ca9372493 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e5c07217bca547b3470a46ae42fb5046432db821c55d26897e0eb5d03a1cd7 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..47985209376521407d59f1730fafb85e2a50a305 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fb2c5e43f4f2cf564d9de0c5cd1d2a09b23c890e95d12318597accddfa8b82c +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/20/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c9b7598d6f9e91ccb98b614ea36e08b03e04a60d --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a3621956d070c85d80bf482be32fe5f1a5dd8498c6f700de23a8dec1009c81 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9a48018a69f93cc8a8765c28beb8424a750a86c9 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d0897385686d2ad874f2d19e1c364d424d51831d5a994359d688aa8ec9b59e5 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..28ec150f614addc5dbf201c8e5d56753c382218a --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:393a29e5ced10b4c8e949607955b1f75bc48eb5775104d14547cc2524eeb3e11 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a8887896f42b554e375ea6844f81eb00d32edfff --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c9a4bd743bf88a62d57049a26997770a203ce64aca079e22d7ec6ea6a1913cd +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/21/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f216729f17ca17eb1604a0fee6db2c89acc51a68 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ed0055320acde8625f0c231189a0dc04262e7c13fd4f61f99963232d109e9f1 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bd930df31f260786bc85db89eb443a2127077583 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06e595f070088ae946e8f5426e6506f4b700bad889b6d90b24b9634d40554f3 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2c4aaad4ce2514a067f5f8e12181667ecf4e95f2 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:770a13202e6bf9f26c584c084f71b0d5084a1fd16e0a4b0e6cf7f4fe54af0457 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..11634c44f11aa6d2f653e7b3044299f7d18500e5 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bb79037cb2617a5ef77e04cd1c5f45bf8b35df301b66020d66231fec2a81fcd +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/22/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0f8df68780c1d0ff14c38299a831f21caa46e6f --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3ac230e3200597d043be3997407d07a9b2176493c32c4c8b365ed174396f1f1 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..acfdae2aa81b6cd16ef3954f746ad0587684bd78 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5af6112e4176ba01d36be7d5ed3ae18a6a6b9c057a426d5655a13497db77d3ed +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3e10cfee3417d9ae0c613a3381afd75fc1725da3 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5dcd862c393709f52f49d71414cc63765482308b8798735aed972289de2a0d7 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d02f4630a13f0bce23f2c9a4017a3082d2287d50 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aa164f423fd39c721794e50fd5013856672ea712b19af087992a7b1cfed00da +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/23/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e7c4cf48829dff312c8228f2eddb03222f2207b --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:832d16834cae680d1a83dc6c3c9c2bc16ce2c3dcdd381d536fb2ae281cee60d3 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6cd81d293e604473798c572b889eae0e96eadde3 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d5aac8abd87770b4d13f66754d60094c0bb98ccc272553897948bd9da8dfb3 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eadb51c7e1ca128c4054ea0913d7b6b32db7cb65 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e3e301b823e1904c6774b4736c07be11c4052e160dce3f3a090826356d75b0 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..67faff556a732ff9fa99d835c38878e61a3ad8e4 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a6834a4b35d9b7630b66dc0f14bd781784aa8c86233c4b4217d762c83eef2e9 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/24/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c634fec6cea71a56970a79301b6ff35b5627dbe6 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b30e8dc85d271fdfe0ff58353845ea72990158b1fd5af755b3e8ca131bdab08 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1fd6c78042bf6c9e172ab190b329767c2b126f6 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:147bbdf8e5787aa068d2b638761fe361726396f8847a246154a1ed5aa4dd441a +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..55b6f9788e67628080f474156e4557c13dfba8b9 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b8b017838ab99ead4e4914c90058582d1db31fab2e6d9bd763f639a3621c5dd +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..873abde08cde13a5b04ea01ae412334130a745aa --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77cb2301c655576564f13d98e963100d49cffa70a35646138f2c8bb76cde1f2e +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/26/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..97b27d99434a78acc25d0604268d2420a6ea618c --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b3883ad1a622abbe877f36ca546b90a286c01cacc0a6ec575df1761c13cf722 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..18838880459a69b2b0b0031d71b1c72363621618 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:951b5b089a1182e5374d8806ed35a01d1038b5915effba2487a93a609901cb30 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..69d87b0d147db6dc89650c648d10151916e9f7aa --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16404c967ca38406044223e1c03b0c070286c4a853f59dbf7b6428cfc4e3691a +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c259444cfaf7d36676a1852979e201921be9b748 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c154112cba3d221a7704a941e019ec4e455891c78e12f443a40b72c951546dc +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/27/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b3e3cca77476b9e8736e1b6c0614e2446076d2fa --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ffc83f83c05d0fbf8c23ddf2a57461f376b76aafb32263abc4cd85d7f79fcf +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f12590f24b838431f88704a75662a89f102b102 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8493e0fa65f8520602f148c00e88c13fe5f3b0c25dbf87f09eb3b03cf8506d16 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c2ef0582da5956aaba5c8d11fc7799f64edefb0 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3640afd2f7ac6f2f93ba6325b441821cddc4ebee0938844aafa8dd0295c3b523 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0337564e3d4ea44de6d03f4c46f1dcbc0ffb7761 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f58d23aa56fa253f635632321333e865b4ef26728648921afd78e2f1598c529c +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/3/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fce0d0a5040c8d423451c3daec845bd2aca560cf --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f6fcb04dec520abec886a00cfa140734c37bbcafa43272cea9024d899a8877 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5fe759dbbbc52b75093e764e1218c7424e4e1d0 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ca53155d816839e93c2d52a9c1af725eab80b9cd33ebd55d8252195379d26f2 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..235e0d6d08e5fd9a288504787b1d631a9fbb6f76 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acb0253fcfd06288944b550d3603a62a0cd7be54a822cce987007cba2f2b0819 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..914ef31afea23d1a69eb91c2942cd89655eeed74 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fb8009664b8eab40986749b78659b1d89c0aeeb658140695e68db4ae6966102 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/5/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/6/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/6/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f06e37ae018356d928c360cfa9c3850423434513 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/6/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acf6547d0da06dbe11475546eb63cf8de87ee7e0733752ff4432af2c863ea509 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5f58fff651187ac7d057354245eac3450ecfc0c5 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b575ce6dc78b2b6a41dac8c7be45c93d0f78be5848e2968a432685dc9c98b4ce +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8271f84fd3a5b3e00cdd37cd20b14ae671fc3e05 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab9076156e38f10c0f1945dd531c69f37edaeba39aaf152417bd89c5052268bb +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a9bba772d1d8d032168013bba3bbf8bed547d5e --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b44121b4db58c93e486173d3de491a2bb7820e7b1395216f91fff2f8c4da5744 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..00ce4d948cd0a58d477259557ab2541ed289ebf4 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61bdeb3883881e7e137199231876904f8c782cbc0085a19a7f9e8db0d1ab9936 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/7/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d52b72e6b6f8ff57a1ac9651079324f0c59ed178 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3be441e52b9c839ad6834b4209bf36e8b717a100df67d574a226052781498d66 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a2b55e6c8b535d032e21fe9a3ad4ab63f11b5799 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55f7261762080859fdb0591be115f608ade536230f5a3c16cd113e3d77bcaff5 +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b42d9290b57ecf008af9355681aef1409ff0f4dc --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39c7616020a553b1fd85b55c33b7e6db5b73ed4bf49626e49e7de090ed505e4d +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ded5ebce46c371fb47e448a4071b21e5427fff1 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c48a5531535148ed7fd212bd78dbeb1d5e15f39f81dcfab92ec318bbb34f4c +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/8/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bbcb4dc87f56375d29da562336cacc5605097212 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7505d8fd165f3f6bdd0b326af40a10cceb8a8d203b9246fbc5a4b847237a901 +size 8388848 diff --git a/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2376711fd1c0410a1c599151ecc1cbc4020025b --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111010559e0c55196fec82fd708b35d5206c61cab779b1b7ffcd1c973e96e28c +size 25166192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..693d2fe478564545e90a5910527a79a7f5d92317 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f9d3665de6db05e508b85895d3b2049d31b270a1ccdefd40c79934f6014a174 +size 23068912 diff --git a/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1c2e3b5b93ee41ed7e45ead9077dbdea3bf5c1d6 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:348a9e4e760f5961d613e3dd10ee7a0519a3d869bf4df5ef16f572b21fb3b659 +size 46137656 diff --git a/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed43/0/model/model/decoder/9/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed43/0/random/tp-0-of-1_dp-0-of-4_pp-0-of-1.pt b/_init_1.5B_seed43/0/random/tp-0-of-1_dp-0-of-4_pp-0-of-1.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e2ff92a97577808d7898ec9acf98564605dce21 --- /dev/null +++ b/_init_1.5B_seed43/0/random/tp-0-of-1_dp-0-of-4_pp-0-of-1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cafa33c7f898af8cfdd14070a86ceb6e82a7e4667f7742eb260461bfa472220c +size 1080 diff --git a/_init_1.5B_seed43/0/random/tp-0-of-1_dp-1-of-4_pp-0-of-1.pt b/_init_1.5B_seed43/0/random/tp-0-of-1_dp-1-of-4_pp-0-of-1.pt new file mode 100644 index 0000000000000000000000000000000000000000..2dba7a6d95fd2669b13d67e2a5f1d2bc70239654 --- /dev/null +++ b/_init_1.5B_seed43/0/random/tp-0-of-1_dp-1-of-4_pp-0-of-1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c767793d2f8cbbe122ed6d6d45d61859b9e7c78f012f40becea9d84a766f26d +size 1080 diff --git a/_init_1.5B_seed43/0/random/tp-0-of-1_dp-2-of-4_pp-0-of-1.pt b/_init_1.5B_seed43/0/random/tp-0-of-1_dp-2-of-4_pp-0-of-1.pt new file mode 100644 index 0000000000000000000000000000000000000000..13ee4024b14178b9d269e0d7012104fc9a6cc689 --- /dev/null +++ b/_init_1.5B_seed43/0/random/tp-0-of-1_dp-2-of-4_pp-0-of-1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe7792d5682fe9b9672a0f9dff4fd43975f3cb836180000e3eb5a809190a859e +size 1080 diff --git a/_init_1.5B_seed43/0/random/tp-0-of-1_dp-3-of-4_pp-0-of-1.pt b/_init_1.5B_seed43/0/random/tp-0-of-1_dp-3-of-4_pp-0-of-1.pt new file mode 100644 index 0000000000000000000000000000000000000000..80a292d765754d0db86f2349e36aeda4565867cf --- /dev/null +++ b/_init_1.5B_seed43/0/random/tp-0-of-1_dp-3-of-4_pp-0-of-1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:456788c887b847f5cba3eb98c3649fe84190ceba1f1ce60dbe40c39ea668703f +size 1080 diff --git a/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e5d39b9ce47c6e81b3a8cc9e33895d24bee6989b --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:818fd891ce851ff4c87b8fcc9eafadc6e188ed1a89483bbd13d7120830464644 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35abb9c7e8d5fa2697906f0a7f0d9acdee2300c6 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:621623f031c4fc68a50c3d2baca2d8cc65cd5086d6708c0ce5b8346a79e8f9f6 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce505d706b033595d38309a45d5de1df5cfb7de3 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aae57a7abccd6d7e7bbbb2fc20b98c78a0419c01bd66ae9d477d2aa16774572 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..47cf89c4c11ff10f109d308935b2b3ade784d0be --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce6aedd51a07aa143aa868e678fd629854043c1e41b917c4d582d369d500c740 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dcd72bd37813d83bddaa2eef262bd8ec131cc8d1 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43bcd371258baef3a02d381777607f3cb905907b5d72df2d0798d87359648393 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f1492170692d6277ad19ac81baeba6aeb9d3a806 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13159aaf6cb0e715a86f39a111543b2948035ea33ad744fa58fc94f1f4adbb61 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a14b63968db4be51226e04072a66811406d66657 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8c430f48b7831e0be675e0d7cd0311568c7f04f3e67a4f4764af5461b28dc4e +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bd0bb495b137041d2423ac951bf431ccb40e7ab8 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa1f4b86d22598846a3480d98ceb0e2add08e5373181d58125a140c500a3a6d2 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1005413d96552b3dcbc34ba1f61160f040051f80 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eb4f47238b1bb7389bac8fc941b1568fc404506c801c6de3bbdebfb66f4e22d +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4c84d84abb47bd0c431ccd8b6fed9dbb2787a80d --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea4465732816faf022336adefcda24f4ab426df1a3e95b414f2efe384e0ba0f3 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa4433e73828c9044be5450a97807692458a134c --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c2979c90834562363bcbfb6f788c18f7b81ab9785773925de01673027895340 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7bf67a4768d4ba4b4c7f55115e7246d2ee74ecd3 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90cd5e76d641c8c859dcd2ace51483aca80bb918c179b9f12d512c6aec8ad3f1 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dca15701c5cb290117eb335f61a9495955afaa63 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feb2194114db95f7bd478848d15d14e6fd09e5079c1a1d95161b82153edeea72 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56d54e232879b9cdafef181c50f2fc970e706eb1 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb2c2b3db36d21aa3b56de43d886f809b88d7c58016aa089a93dd2225b20822 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..287b7c4c3dd36f88695ee752cccfa028c07dc596 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b5beef0b3c32329a8abe351f36fc24883eaa739dd835a58e2d4d11bca56820 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/22/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da4bc61cae3537366192ee1b2ce1c31f535c87eb --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14bc9b9d854e7a70f62c4a63553223819dfd71e057f3b6bc542367648626ca87 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..719ec14cde809187e0f4328fd48772bfb0c8204c --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fff1e487565aa560852b06b926889262e0d84a7ba57b8d4afeb4154dace2c2d4 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5674bee99890fc7b767472b04ba69000417e7bb3 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5f4e1ef371cc4bb0b94c6ff2dd425af5231288ee8241fba76049d3d28b95135 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..932cef8dea7ec0fc6db44baf393a2d7e90761f27 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4345b1e03983723658c524fd9f0951299b7e82a70737a8cac2b6c1755caff6ac +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f185fc9303b46f53163cf29ebfcb6cb96be0947b --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad53a855460806a095fc718e1d5bfbf22b511f44c8f4e5ec33ef4d17353f7dbf +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/7/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d2d2bbebc18d31eeb4be3429d88c7d348edbd096 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daa64e3ccefa60c9388dbdb683366b8750a353346d6fd46fd0e81a69d941703c +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..26d66245a10ced55a0568d52cdd0af5ea7e0569f --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d7356393555a66a3970c7764e06c998c690b7a1cc0aa29c0f5ea04e316d424c +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..035c10ceab60107427713a9e50d86e3e9ac06805 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39c603bfc6f7a8fb80cd0299c92ec4173623b67a4d1d6b9d09c780656967131e +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e319be6054bf16c17cc7789dd8f97210b273878e --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6dbc34553ad402879a2d967ce5002d64d8179e935be4549631fe161642b60be +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/8/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/final_layer_norm/pp_block/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/final_layer_norm/pp_block/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/final_layer_norm/pp_block/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192